[training]
patience = 10000
eval_frequency = 200
dropout = 0.2
init_tok2vec = null
vectors = null
max_epochs = 100
orth_variant_level = 0.0
gold_preproc = true
max_length = 0
use_gpu = 0
scores = ["tags_acc", "uas", "las"]
score_weights = {"las": 0.8, "tags_acc": 0.2}
limit = 0
seed = 0
accumulate_gradient = 2

[training.batch_size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001

[optimizer]
@optimizers = "Adam.v1"
learn_rate = 0.001
beta1 = 0.9
beta2 = 0.999

[nlp]
lang = "en"
vectors = ${training:vectors}

[nlp.pipeline.tok2vec]
factory = "tok2vec"

[nlp.pipeline.tagger]
factory = "tagger"

[nlp.pipeline.parser]
factory = "parser"

[nlp.pipeline.tagger.model]
@architectures = "spacy.Tagger.v1"

[nlp.pipeline.tagger.model.tok2vec]
@architectures = "spacy.Tok2VecTensors.v1"
width = ${nlp.pipeline.tok2vec.model:width}

[nlp.pipeline.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
hidden_width = 64
maxout_pieces = 3

[nlp.pipeline.parser.model.tok2vec]
@architectures = "spacy.Tok2VecTensors.v1"
width = ${nlp.pipeline.tok2vec.model:width}

[nlp.pipeline.tok2vec.model]
@architectures = "spacy.HashEmbedBiLSTM.v1"
pretrained_vectors = ${nlp:vectors}
width = 96
depth = 4
embed_size = 2000
subword_features = true
maxout_pieces = 3